Predicting Stock Market Returns Based on the Content of Annual Report Narrative: A New Anomaly

43 Pages Posted: 31 Jul 2014 Last revised: 20 Aug 2015

Date Written: July 30, 2014

Abstract

This paper uses the tools of computational linguistics to analyze the qualitative part of annual reports of UK listed companies. More specifically, the frequency of words associated with different language indicators is measured and used to forecast future stock returns. We find that two of these indicators, capturing ‘activity’ and ‘realism’, predict subsequent price increases, even after controlling for a wide range of factors. Elevated values of these two linguistic variables, however, are not symptomatic of exacerbated risk. Consequently, investors are advised to peruse annual report narratives, as they contain valuable information that may not yet have been discounted in the prices.

Keywords: Content Analysis, Annual Reports, Stock Market Returns

JEL Classification: M41; G12; G14

Suggested Citation

Wisniewski, Tomasz Piotr and Yekini, Liafisu, Predicting Stock Market Returns Based on the Content of Annual Report Narrative: A New Anomaly (July 30, 2014). Available at SSRN: https://ssrn.com/abstract=2474061 or http://dx.doi.org/10.2139/ssrn.2474061

Tomasz Piotr Wisniewski (Contact Author)

Open University, UK ( email )

Walton Hall
Milton Keynes, Buckinghamshire MK7 6AA
United Kingdom

Liafisu Yekini

Coventry University ( email )

William Morris building
Coventry Business School, Gosford Street
Coventry, CV1 5DL
United Kingdom

Register to save articles to
your library

Register

Paper statistics

Downloads
277
rank
107,950
Abstract Views
1,312
PlumX Metrics
!

Under construction: SSRN citations will be offline until July when we will launch a brand new and improved citations service, check here for more details.

For more information